A Fast Load-shedding Algorithm for Power System based on Artificial Neural Network

When the power system breaks down or the unit is shut down due to equipment maintenance, emergency control measures such as load cutting should be taken to ensure the stable operation of the system. With the expansion of power grid scale and the complexity of power grid structure caused by new energy grid-connection, the traditional physical modeling method is difficult to accurately reproduce the characteristics of the power grid, and it is impossible to get an effective load cutting scheme in a short time. From the perspective of data analysis, this paper analyzes and sorts out the operation environment data of power grid, and generates the sample data set for model training. Based on the sample data, the artificial neural network was trained, and the potential operation characteristics of the power grid were extracted by means of supervised learning, so as to quickly obtain the load shedding schemes under different operation states of the power grid. The effectiveness of the proposed method is verified by comparing the proposed method with the traditional one based on an example system.